ClawHub
Back to skill

Security audit

X-ray

Security checks across malware telemetry and agentic risk

Overview

This skill performs a disclosed, read-only project scan and creates local report files, with no evidence of hidden network access, persistence, credential use, or destructive behavior.

Install this only if you want an agent to inspect the contents and file names of the project you run it in and create local report files. Run it from the intended repository root, and avoid using it on directories that contain secrets or unrelated private material.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to read many project files and generate an HTML report, which implies file read and file write capabilities, but it does not declare permissions explicitly. Undeclared capabilities are dangerous because they bypass least-privilege expectations and can cause the agent to access or create files without clear user or platform consent boundaries.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The invocation/workflow is broad: it says to scan the current project, read generated data, then further read README, config files, entry points, and key source files without clear scoping or trigger constraints. In practice this can lead to over-collection of repository contents, including unexpected sensitive files or large areas of the workspace, especially when 'current project' is ambiguous.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.